Fraudulent User Detection Via Behavior Information Aggregation Network (BIAN) On Large-Scale Financial Social Network

TL;DR

This paper introduces BIAN, a novel graph neural network that effectively aggregates user behavior information for fraud detection in large-scale financial social networks, outperforming existing models.

Contribution

The paper proposes BIAN, a new GNN model that incorporates behavior-based neighbor aggregation, improving fraud detection accuracy in financial social networks.

Findings

BIAN achieves a 10.2% AUROC improvement over state-of-the-art models.

Behavior-based neighbor aggregation enhances fraud detection performance.

Experimental results validate BIAN's effectiveness on real-world data.

Abstract

Financial frauds cause billions of losses annually and yet it lacks efficient approaches in detecting frauds considering user profile and their behaviors simultaneously in social network . A social network forms a graph structure whilst Graph neural networks (GNN), a promising research domain in Deep Learning, can seamlessly process non-Euclidean graph data . In financial fraud detection, the modus operandi of criminals can be identified by analyzing user profile and their behaviors such as transaction, loaning etc. as well as their social connectivity. Currently, most GNNs are incapable of selecting important neighbors since the neighbors' edge attributes (i.e., behaviors) are ignored. In this paper, we propose a novel behavior information aggregation network (BIAN) to combine the user behaviors with other user features. Different from its close "relatives" such as Graph Attention Networks (GAT) and Graph Transformer Networks (GTN), it aggregates neighbors based on neighboring edge attribute distribution, namely, user behaviors in financial social network. The experimental results on a real-world large-scale financial social network dataset, DGraph, show that BIAN obtains the 10.2% gain in AUROC comparing with the State-Of-The-Art models.